Vision transformer properties
Vision transformers are not just a replacement for CNNs and RNNs. They have some interesting properties.
Posts by Tag
- machine-learning 13
- computer-vision 4
- social-impact 3
- explainability 3
- interpretability 3
- transformers 3
- data-science 2
- bias 2
- failure 2
- shap 2
- artificial-intelligence 1
- fairness 1
- accuracy 1
- roc 1
- image-classification 1
- deep-learning 1
- natural-language-processing 1
- nlp 1
- jupyter-notebooks 1
- python 1
- generative-ai 1
- llm 1
- summarization 1
- prompt-engineering 1
- writing 1
- reading 1
- papers 1
machine-learning
Understanding transformers in one morning
Transformers: from zero to hero in one morning (or at least know enough to discuss transformers intelligently and apply them to your projects).
Applications of transformers in computer vision
The evolution of transformers, their application in natural language processing (NLP), their surprising effectiveness in computer vision, ending with applica...
Machine learning interpretability with feature attribution
A review of feature attribution, a technique to interpret model predictions. First, it reviews commonly-used feature attribution methods, then demonstrates f...
An overview of deep learning for image processing
Deep learning (large, multi-layered neural networks) have been successfully applied to computer vision tasks. This article reviews its origins, the evolution...
Exploring SHAP explanations for image classification
How to interpret predictions of an image classification neural network using SHAP.
Machine learning, but not understanding
In the expression ‘machine learning’, are the machines actually learning anything? Let’s explore what ‘learning’ means for machine learning, guided by Melani...
What is “model accuracy”, really?
A model’s accuracy is an incomplete view of of the model’s performance. This article shows how it can be misleading.
Fairness in machine learning: a reading list
A list of resources to understand concepts and applications of fairness in machine learning (ML).
Explainability: end-users considerations
If we assume that explaining to the end-users how a machine learning (ML) model makes its predictions increases their trust on that model, the question is th...
Would you trust AI to do [X]?
Exploring ‘robustness’ as a factor to trust AI products, with examples of how difficult it is to create robust AI products.
Bias in data science and machine learning
Of all the problems that may crop up in the machine learning lifecycle (acquire data, train a model, test the model, deploy, and monitor), biased data is the...
Artificial intelligence and jobs
A review of articles that explore the effect of AI on jobs, based on an article from The Economist.
computer-vision
Vision transformer properties
Vision transformers are not just a replacement for CNNs and RNNs. They have some interesting properties.
Applications of transformers in computer vision
The evolution of transformers, their application in natural language processing (NLP), their surprising effectiveness in computer vision, ending with applica...
An overview of deep learning for image processing
Deep learning (large, multi-layered neural networks) have been successfully applied to computer vision tasks. This article reviews its origins, the evolution...
Exploring SHAP explanations for image classification
How to interpret predictions of an image classification neural network using SHAP.
explainability
Machine learning interpretability with feature attribution
A review of feature attribution, a technique to interpret model predictions. First, it reviews commonly-used feature attribution methods, then demonstrates f...
Exploring SHAP explanations for image classification
How to interpret predictions of an image classification neural network using SHAP.
Explainability: end-users considerations
If we assume that explaining to the end-users how a machine learning (ML) model makes its predictions increases their trust on that model, the question is th...
interpretability
Machine learning interpretability with feature attribution
A review of feature attribution, a technique to interpret model predictions. First, it reviews commonly-used feature attribution methods, then demonstrates f...
Exploring SHAP explanations for image classification
How to interpret predictions of an image classification neural network using SHAP.
Explainability: end-users considerations
If we assume that explaining to the end-users how a machine learning (ML) model makes its predictions increases their trust on that model, the question is th...
transformers
Vision transformer properties
Vision transformers are not just a replacement for CNNs and RNNs. They have some interesting properties.
Understanding transformers in one morning
Transformers: from zero to hero in one morning (or at least know enough to discuss transformers intelligently and apply them to your projects).
Applications of transformers in computer vision
The evolution of transformers, their application in natural language processing (NLP), their surprising effectiveness in computer vision, ending with applica...
data-science
Writing good Jupyter notebooks
How to write well-structured, understandable, flexible, and resilient Jupyter notebooks.
Bias in data science and machine learning
Of all the problems that may crop up in the machine learning lifecycle (acquire data, train a model, test the model, deploy, and monitor), biased data is the...
bias
Fairness in machine learning: a reading list
A list of resources to understand concepts and applications of fairness in machine learning (ML).
Bias in data science and machine learning
Of all the problems that may crop up in the machine learning lifecycle (acquire data, train a model, test the model, deploy, and monitor), biased data is the...
failure
Machine learning, but not understanding
In the expression ‘machine learning’, are the machines actually learning anything? Let’s explore what ‘learning’ means for machine learning, guided by Melani...
Would you trust AI to do [X]?
Exploring ‘robustness’ as a factor to trust AI products, with examples of how difficult it is to create robust AI products.
shap
Machine learning interpretability with feature attribution
A review of feature attribution, a technique to interpret model predictions. First, it reviews commonly-used feature attribution methods, then demonstrates f...
Exploring SHAP explanations for image classification
How to interpret predictions of an image classification neural network using SHAP.
artificial-intelligence
Artificial intelligence and jobs
A review of articles that explore the effect of AI on jobs, based on an article from The Economist.
fairness
Fairness in machine learning: a reading list
A list of resources to understand concepts and applications of fairness in machine learning (ML).
accuracy
What is “model accuracy”, really?
A model’s accuracy is an incomplete view of of the model’s performance. This article shows how it can be misleading.
roc
What is “model accuracy”, really?
A model’s accuracy is an incomplete view of of the model’s performance. This article shows how it can be misleading.
image-classification
Exploring SHAP explanations for image classification
How to interpret predictions of an image classification neural network using SHAP.
deep-learning
An overview of deep learning for image processing
Deep learning (large, multi-layered neural networks) have been successfully applied to computer vision tasks. This article reviews its origins, the evolution...
natural-language-processing
Understanding transformers in one morning
Transformers: from zero to hero in one morning (or at least know enough to discuss transformers intelligently and apply them to your projects).
nlp
Understanding transformers in one morning
Transformers: from zero to hero in one morning (or at least know enough to discuss transformers intelligently and apply them to your projects).
jupyter-notebooks
Writing good Jupyter notebooks
How to write well-structured, understandable, flexible, and resilient Jupyter notebooks.
python
Writing good Jupyter notebooks
How to write well-structured, understandable, flexible, and resilient Jupyter notebooks.
generative-ai
Using LLMs to summarize GitHub issues
A learning exercise on using large language models (LLMs) for summarization. It uses GitHub issues as a practical use case that we can relate to.
llm
Using LLMs to summarize GitHub issues
A learning exercise on using large language models (LLMs) for summarization. It uses GitHub issues as a practical use case that we can relate to.
summarization
Using LLMs to summarize GitHub issues
A learning exercise on using large language models (LLMs) for summarization. It uses GitHub issues as a practical use case that we can relate to.
prompt-engineering
Using LLMs to summarize GitHub issues
A learning exercise on using large language models (LLMs) for summarization. It uses GitHub issues as a practical use case that we can relate to.
writing
Improve writing by learning how to read
Turn the advice in “How to Read a Paper” around to write a good paper.
reading
Improve writing by learning how to read
Turn the advice in “How to Read a Paper” around to write a good paper.
papers
Improve writing by learning how to read
Turn the advice in “How to Read a Paper” around to write a good paper.
social-impact
Fairness in machine learning: a reading list
6 minute read
A list of resources to understand concepts and applications of fairness in machine learning (ML).
Bias in data science and machine learning
7 minute read
Of all the problems that may crop up in the machine learning lifecycle (acquire data, train a model, test the model, deploy, and monitor), biased data is the...
Artificial intelligence and jobs
4 minute read
A review of articles that explore the effect of AI on jobs, based on an article from The Economist.